Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1660 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1550. Min Range: -1.1550

Max Act: 1.1550. Min Act: -0.0000

Data Index: 265318 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9954. Min Act: -0.0000

Data Index: 582284 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1728791 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1812594 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1324164 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.8294. Min Act: -0.0000

Data Index: 131152 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9838. Min Act: -0.0000

Data Index: 835698 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1788299 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 1.1550. Min Range: -1.1550

Max Act: 1.0297. Min Act: -0.0000

Data Index: 909500 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9127. Min Act: -0.0000

Data Index: 334808 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1690152 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9097. Min Act: -0.0000

Data Index: 16745 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9567. Min Act: -0.0000

Data Index: 761843 (The Pile)

Max Activating Token Index: 492

Text #13

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9015. Min Act: -0.0000

Data Index: 692792 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.8672. Min Act: -0.0000

Data Index: 489135 (The Pile)

Max Activating Token Index: 502

Text #15

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1186821 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.8684. Min Act: -0.0000

Data Index: 258631 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.8039. Min Act: -0.0000

Data Index: 463246 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1799940 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1703356 (The Pile)

Max Activating Token Index: 607